SkillFM: Generating Skills for LLM Agents via Latent Flow Matching
Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with indirect and delayed feedback. We introduce SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills d...
Zu-Ming Zhang, Jie He, Yi-Zhe Zhang et al.
· 0 citations